© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 39431
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "combine" in various forms, indicating a focus on the concept of combination or integration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibbean
    -0.08
    اÙĤ
    -0.08
    /ph
    -0.07
    iminal
    -0.07
    EOS
    -0.07
    itect
    -0.07
    isman
    -0.07
    rang
    -0.07
    irit
    -0.07
    ypy
    -0.07
    POSITIVE LOGITS
    tures
    0.08
    -sama
    0.07
    itarian
    0.07
    wealth
    0.07
     effort
    0.07
     efforts
    0.07
    659
    0.07
     forces
    0.07
    ercial
    0.07
    icut
    0.06
    Activations Density 0.019%

    No Known Activations